MEMFOF

MEMFOF is a memory-efficient multi-frame optical flow network from the MSU Graphics & Media Lab (ICCV 2025 Highlight). It reads three frames, t-1, t and t+1, and predicts the flow of the middle frame, aimed at Full HD video. It is the one flow family in LibreYOLO that reads a three-frame window.

Task
optical flow
Dimensioni
m at 1920 px
Installa
pip install libreyolo
Livello di supporto
Solo inferenza, dalla v1.8.0. Solo predizione, validazione ed esportazione. Le funzionalità di addestramento non si applicano.
Origine
MEMFOF di MSU Graphics & Media Lab, BSD-3-Clause. Articolo, sorgente
Licenze
Codice MIT, pesi BSD-3-Clause. Uso commerciale

MEMFOF is a RAFT descendant that predicts the backward (t to t-1) and forward (t to t+1) flow of the middle frame in one pass. LibreYOLO reports the forward flow as Results.flow; the backward flow is computed but kept out of the task contract for now. The runner hands it the (t-1, t, t+1) window and repeats frame 0 as t-1 at the start of a sequence, so you still pass an ordinary list, folder or video. Pick it for real-world video at high resolution.

Install

MEMFOF needs no optional extra. Everything it imports is in the base install.

bash
pip install libreyolo

Predict

Weights download from the LibreYOLO Hugging Face organization on first use. The class LibreMEMFOF is also exported from libreyolo if you prefer to build the model directly.

Python
from libreyolo import LibreYOLO model = LibreYOLO("LibreMEMFOFm-flow.pt")   # weights download on first useresults = model(["frame_0001.jpg", "frame_0002.jpg"]) flow = results[0].flowprint(flow.data.shape)        # (H, W, 2) float32, (dx, dy) in pixelsprint(flow.mean_magnitude)    # mean displacement in pixels
Video
from libreyolo import LibreYOLO model = LibreYOLO("LibreMEMFOFm-flow.pt") # N frames give N - 1 results; result i is the flow from frame i to i + 1.for result in model("video.mp4", stream=True, save=True, save_flow=True):    print(result.flow.max_magnitude)
CLI
libreyolo predict model=LibreMEMFOFm-flow.pt source=frame_0001.jpg,frame_0002.jpg save=truelibreyolo predict model=LibreMEMFOFm-flow.pt source=video.mp4 save=true arrows=true save_flow=true

Flow needs at least two frames: a single image raises. A list of images, a directory sorted by name, a video or a stream is one sequence, and N frames give N - 1 results. result.flow is a FlowField with an (H, W, 2) float32 array on the original canvas of the first frame; flow.data[y, x] is (dx, dy) in pixels, +x right and +y down. MEMFOF fills no confidence map, so flow.confidence is None. result.boxes is None. save=True writes the Middlebury colour wheel, arrows=True or warp=True pick the other views, and save_flow=True also writes each pair's raw field as a .flo file. The optical flow task page describes the payload and views in full.

Variants

One architecture (ResNet-34 FPN), size m, with six checkpoints:

FileUpstream checkpoint
LibreMEMFOFm-flow.ptMEMFOF-Tartan-T-TSKH, recommended by the authors for real-world video (canonical)
LibreMEMFOFm-flow-tartan-t.ptan earlier published training stage
LibreMEMFOFm-flow-tartan.ptan earlier published training stage
LibreMEMFOFm-flow-kitti.ptKITTI fine-tune
LibreMEMFOFm-flow-sintel.ptSintel fine-tune
LibreMEMFOFm-flow-spring.ptSpring fine-tune

Frames run at native resolution with upstream's replicate padding to a multiple of 16. Frames whose long side exceeds imgsz (default 1920, MEMFOF's Full HD target) are downscaled first and the field is scaled back. Inference is fp32 with 8 refinement iterations, upstream's defaults.

Training is not offered: train() raises NotImplementedError.

Validate

val() runs the shared flow validator on a flow dataset (frames per sequence folder, Middlebury .flo, KITTI 16-bit PNG or .npy ground truth; see the dataset format). It reports the mean end-point error metrics/epe, metrics/px1 and metrics/px3 (share of valid pixels under 1 and 3 px of error) and the KITTI outlier rate metrics/fl_all.

Python
from libreyolo import LibreYOLO model = LibreYOLO("LibreMEMFOFm-flow.pt")metrics = model.val(data="my_flow.yaml") print(metrics["metrics/epe"])      # mean end-point error, pixelsprint(metrics["metrics/px1"])      # share of pixels under 1 px errorprint(metrics["metrics/fl_all"])   # KITTI outlier rate
CLI
libreyolo val model=LibreMEMFOFm-flow.pt data=my_flow.yaml

Export

TaskONNXTorchScriptExecuTorchTensorRTOpenVINOPaddleMNNRKNNAxelerancnnTFLiteCoreMLCore AI
Optical flowOptical flow to ONNX: non supportatoOptical flow to TorchScript: non supportatoOptical flow to ExecuTorch: non supportatoOptical flow to TensorRT: non supportatoOptical flow to OpenVINO: non supportatoOptical flow to Paddle: non supportatoOptical flow to MNN: non supportatoOptical flow to RKNN: non supportatoOptical flow to Axelera: non supportatoOptical flow to ncnn: non supportatoOptical flow to TFLite: non supportatoOptical flow to CoreML: non supportatoOptical flow to Core AI: non supportato

Export is not available yet for any format. Optical flow export is blocked until the two-input graph (image1, image2) and the backend vector-rescale contract of the flow task are implemented for a family.

Checkpoints

Every published weight file for this family.

FileLicenza dei pesi
Optical flow
LibreMEMFOFm-flow.ptbsd-3-clause
LibreMEMFOFm-flow-kitti.ptbsd-3-clause
LibreMEMFOFm-flow-sintel.ptbsd-3-clause
LibreMEMFOFm-flow-spring.ptbsd-3-clause
LibreMEMFOFm-flow-tartan.ptbsd-3-clause
LibreMEMFOFm-flow-tartan-t.ptbsd-3-clause

Oggi tutti i file elencati sopra sono presenti nell<link>organizzazione LibreYOLO</link> e vengono scaricati al primo utilizzo.

Licensing

Controlla la licenza nel repository Hugging Face degli specifici pesi che scarichi. Ogni checkpoint nell<link>organizzazione LibreYOLO</link> ne include una e non è sempre la stessa per tutta la famiglia. Quel repository è la fonte autorevole; il riepilogo seguente descrive le condizioni applicabili al momento dellultima verifica di questa pagina.

Questa è una descrizione delle licenze coinvolte, non una consulenza legale. Se la risposta è importante a fini commerciali, leggi personalmente le licenze e chiedi una consulenza indipendente.

Lavoro originale
MEMFOF, MSU Graphics & Media Lab
Licenza upstream
BSD-3-Clause
Codice LibreYOLO
MIT
Pesi
BSD-3-Clause, ripubblicati su huggingface.co/LibreYOLO
Interpretazione
BSD-3-Clause is a permissive license: the code and weights can be used in commercial and closed-source products. Redistributions must keep the copyright notice, the license conditions and the disclaimer, and the authors' names may not be used to endorse derived products without permission. The upstream inference code at commit a51de9fc is vendored under libreyolo/models/memfof/_vendor/ with its BSD-3-Clause LICENSE; its gma.py attention modules come from GMA (zacjiang/GMA) under the WTFPL, shipped as LICENSE-GMA. LibreYOLO's wrapper code is MIT. The upstream checkpoints on Hugging Face (egorchistov/optical-flow-MEMFOF-*) are tagged bsd-3-clause but ship no license file, so LibreYOLO mirrors the six converted checkpoints (canonical, kitti, sintel, spring, tartan, tartan-t) under the code repository's BSD-3-Clause license. No gating; inference only.

MEMFOF is the work of the MSU Graphics & Media Lab. The upstream inference code is vendored under its BSD-3-Clause licence; its attention modules come from GMA under the WTFPL. The upstream checkpoints on Hugging Face are tagged bsd-3-clause but ship no licence file, so LibreYOLO mirrors the six converted checkpoints under the code repository's BSD-3-Clause licence, without gating. BSD-3-Clause allows commercial and closed-source use as long as the copyright notice, conditions and disclaimer are kept.

Citation

@article{bargatin2025memfof,
  title={MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation},
  author={Bargatin, Vladislav and Chistov, Egor and Yakovenko, Alexander and Vatolin, Dmitriy},
  journal={arXiv preprint arXiv:2506.23151},
  year={2025}
}

Copiato dal blocco di citazione degli autori disponibile su github.com/msu-video-group/memfof.

Verificato con LibreYOLO v1.8.0. Le tabelle di supporto, i checkpoint e i dati dei benchmark in questa pagina vengono generati dalla libreria rilasciata e dai pesi pubblicati, non scritti a mano.